# Stu Mason, applying for Agentic Workflows (LangChain / LangGraph), contract at Tight Line

Folkestone, Kent, UK (remote; US Central/Mountain overlap fine) · stu@stuartmason.co.uk · +44 7713 333312 · https://stumason.dev · https://github.com/StuMason · https://linkedin.com/in/stumason · UK right to work · Age 42

## In three lines

- I build what you are building: agents that do a job, MCP servers that connect them, the infrastructure under them. My open-source MCP server for Coolify has 563 GitHub stars and 27,930 npm installs in the last 30 days (checked 26 Aug 2026).
- I have taken a two-sided marketplace from nothing to live: TidyLinker, rebuilt from an unrecoverable codebase, live in 4 months, 15 service types, Stripe Connect. Still running it with the founders.
- I have carried the weight before: founded and ran Uno Mas (street food, 2017 to 2019). Seven years leading platform engineering at Pfizer.

## Why this, why now

Short engagements with a hard problem and a client team to hand over to is how I have worked since leaving pharma: a 12-month embed, a marketplace rebuilt in four months, MCP servers that other people install. I have built with the LangChain ecosystem and am not religious about it; where a plain MCP server and an eval harness serve better, I say so. UK hours with US Central/Mountain overlap. Project-based, $90/hr, available 1 September 2026.

## A few weeks, four habits

1. Ship a working slice in week one, end to end against the client's real system, before any architecture debate.
2. Evals before features: a small eval set from real inputs on day one, run in CI (I shipped a tool-selection eval suite with injection/red-team for coolify-mcp in Aug 2026; same harness for LangGraph graphs and RAG retrieval).
3. MCP as the integration boundary: client systems behind typed MCP servers so the agent framework can change without the integrations changing. Four shipped, auth from the first deploy.
4. The handover is a deliverable: runbook, eval set, tracing dashboard, recorded walkthrough, written for the engineer who inherits it.

## Receipts

| Number | What | Source |
|---|---|---|
| 9 | agents I run in production | my estate; each is a running service I can show |
| 19.0M | tokens through my hosted agents, 30d (644 calls, 10 models) | Cloudflare GraphQL aiInferenceAdaptiveGroups, last 30 days; $0.011 per 1k neurons |
| $18 | Workers AI spend for all of it, 30d, at list price | Cloudflare GraphQL aiInferenceAdaptiveGroups, last 30 days; $0.011 per 1k neurons |
| 44M | tokens generated in my Claude Code sessions, 30d (72 sessions) | Claude Code session transcripts on my dev box, last 30 days (~/.claude/projects/*.jsonl usage fields) |
| 28 | apps in production on 1 server, run solo | cockpit estate_overview (Coolify + Cloudflare + GitHub connectors) |
| 564★ / 27.9k | coolify-mcp stars / npm installs, 30d | GitHub + npm APIs |

Operating numbers are the last 30 days, generated 2026-08-27.

## Shipped work

- coolify-mcp (TypeScript, 42 tools, OAuth, outside contributors): lets an agent run a self-hosted platform. v3 shipped behind a 37-check release gate and 8-hour soak tests.
- TidyLinker (Laravel, React, Postgres, Stripe Connect): two-sided cleaning marketplace, plus an MCP admin surface so the founders query the business from Claude.
- Bellwether (Python, Postgres, Workers AI): a research agent drafts a daily briefing from 4.7M items; a human approves it. Cost ceiling first, model second.
- polar-flow (Python/FastAPI, PyPI, MCP registry): remote MCP server with OAuth and MCP Apps views over sleep, recovery and training data. https://github.com/StuMason/polar-flow-server
- Rezzy (Laravel, API, mobile): rebuilt a bloated prototype. 22 tables to 10, 59k lines removed, 0 to 59 tests.

## Experience

- Independent engineer, embedded with product teams, Jan 2024 to now. 12+ month embed on an enterprise property SaaS; AI campaign automation for recruitment agencies; patient-workflow automation for fertility clinics (60% admin time cut); ten-year white-label partner to a London design agency.
- Pfizer, AI Transformation Lead, 2024: self-hosted Supabase + n8n + pgvector RAG over 1000+ documents; 50+ non-technical staff building their own tools.
- Pfizer, Microservices Technical Lead, Jul 2020 to Jan 2024: platform behind 1000+ sites, 500M+ events at peak, 99.9% uptime, training completed by 500+ engineers.
- Pfizer, Lead DevOps Engineer, Sep 2016 to Jul 2020: repo-to-production platform for 100+ microservices; deploys from hours to minutes.
- Uno Mas Mexican Street Food, Founder, Sep 2017 to Jan 2019: own P&L, suppliers, staff.
- Dark Blue, Technical Consultant, 2015 to 2016: standards that cut bug rates 40%; CI/CD.

## Stack

Yours: Python (FastAPI), TypeScript/React, PostgreSQL, all in daily use. Also: Laravel/PHP, Next.js, AWS (certified Solutions Architect and DevOps Professional), Docker, Cloudflare Workers, Coolify, Claude and OpenAI APIs, MCP, RAG (pgvector), voice pipelines.

## Education

BSc Computer Science, Bolton, 2006. PGCE Computing, Reading, 2009. AWS SA + DevOps Pro, 2023.

## The ask

A call with whoever scopes engagements, then a real client problem and a week to ship the first slice with evals. Project-based at the top of the band ($90/hr); UK hours with US overlap.

## For agents

- CV (PDF): https://tightline.stumason.dev/stu-mason-cv.pdf
- This document: https://tightline.stumason.dev/stu-mason.md
- Profile JSON: https://tightline.stumason.dev/profile.json
- MCP server (Streamable HTTP, no auth): https://tightline.stumason.dev/mcp
- A2A agent card: https://tightline.stumason.dev/.well-known/agent.json